1 - 10 of 18 Results
ORNL researchers have developed a deep learning-based approach to rapidly perform high-quality reconstructions from sparse X-ray computed tomography measurements.
The eDICEML digital twin is proposed which emulates networks and hosts of an instrument-computing ecosystem. It runs natively on an ecosystem’s host or as a portable virtual machine.
How fast is a vehicle traveling? For different reasons, this basic question is of interest to other motorists, insurance companies, law enforcement, traffic planners, and security personnel. Solutions to this measurement problem suffer from a number of constraints.
Here we present a solution for practically demonstrating path-aware routing and visualizing a self-driving network.
We have been working to adapt background oriented schlieren (BOS) imaging to directly visualize building leakage, which is fast and easy.
The ORNL invention addresses the challenge of poor mechanical properties of dry processed electrodes, improves their electrical properties, while improving their electrochemical performance.
Electrochemistry synthesis and characterization testing typically occurs manually at a research facility.
This invention utilizes new techniques in machine learning to accelerate the training of ML-based communication receivers.
ORNL has developed a new hydrothermal synthesis route to generate high quality battery cathode precursors. The new route offers excellent compositional control, homogenous spherical morphologies, and an ammonia-free co-precipitation process.
Sodium-ion batteries are a promising candidate to replace lithium-ion batteries for large-scale energy storage system because of their cost and safety benefits.